Bỏ qua để đến nội dung

Release Notes

Nội dung này hiện chưa có sẵn bằng ngôn ngữ của bạn.

What changed in each release, filtered to what matters for operators running an edge box. For how versions are reported on your device, see Versions & Updates.

Execution-provider modes for edge hardware

Section titled “Execution-provider modes for edge hardware”
  • The runtime now classifies its execution provider explicitly: TensorRT, CUDA, or CPU. GPU boxes prioritize GPU acceleration by default and fall back gracefully if a GPU library is unavailable.
  • A strict mode can turn a silent CPU fallback into a startup failure, so a GPU box never quietly runs on CPU.
  • The dashboard now shows the active execution provider so you can confirm what your box is really using. See Monitoring.
  • A new CSV output writes prediction results to rotating CSV files, with configurable file size, rotation, and flush behavior. See Output Datasources.
  • Honest CPU temperature. When a box has no readable CPU thermal sensor, the dashboard now shows N/A instead of a misleading 0 °C.
  • Disk space reclamation. The metrics database now returns freed space to the operating system after its retention sweep, and caps total rows so a traffic burst can’t fill the disk.
  • Accurate runtime status. The Model Manager runtime card no longer shows a false “Desync” when idle or warming up.
  • All services now run as non-root users.
  • The web frontend listens on an unprivileged port internally (host ports are unchanged).

v0.5 — Inference observability dashboard

Section titled “v0.5 — Inference observability dashboard”
  • Latency decomposition (queue / pre-process / model exec / post-process)
  • Window & bucket controls for time aggregation
  • Per-model latency thresholds
  • OPC-UA, MQTT, and Modbus TCP adapters
  • Rate limiting and backpressure reporting
  • Model versioning and staged promotion
  • Live, push-driven dashboard updates
  • Role-based access control and an audit log